activity
20202023
most citedUnpacking Reward Shaping: Understanding the Benefits of Reward Engineering on Sample Complexity

12 citations · 45 across the 16 of their papers we have counts for

collaborators

16 papers

cs.HC2023

Empirical Measurement of Aesthetic Experience of Music

Abhishek Gupta, C. M. Markan

Chills or goosebumps, also called frisson, is a phenomenon that is often associated with an aesthetic experience e.g., music or some other ecstatic experience. The temporal and spa…

cs.RO20225 cited

Learning Robust Real-World Dexterous Grasping Policies via Implicit Shape Augmentation

Zoey Qiuyu Chen, Karl Van Wyk, Yu-Wei Chao +4

Dexterous robotic hands have the capability to interact with a wide variety of household objects to perform tasks like grasping. However, learning robust real world grasping polici…

cs.LG202212 cited

Unpacking Reward Shaping: Understanding the Benefits of Reward Engineering on Sample Complexity

Abhishek Gupta, Aldo Pacchiano, Yuexiang Zhai +2

Reinforcement learning provides an automated framework for learning behaviors from high-level reward specifications, but in practice the choice of reward function can be crucial fo…

cs.CV202210 cited

DexTransfer: Real World Multi-fingered Dexterous Grasping with Minimal Human Demonstrations

Zoey Qiuyu Chen, Karl Van Wyk, Yu-Wei Chao +4

Teaching a multi-fingered dexterous robot to grasp objects in the real world has been a challenging problem due to its high dimensional state and action space. We propose a robot-l…

cs.IT2022

Impact of Multiple Fully-Absorbing Receivers in Molecular Communications

Nithin V. Sabu, Abhishek K. Gupta, Neeraj Varshney +1

Molecular communication is a promising solution to enable intra-body communications among nanomachines. However, malicious and non-cooperative receivers can degrade the performance…

cs.RO2022

Demonstration-Bootstrapped Autonomous Practicing via Multi-Task Reinforcement Learning

Abhishek Gupta, Corey Lynch, Brandon Kinman +3

Reinforcement learning systems have the potential to enable continuous improvement in unstructured environments, leveraging data collected autonomously. However, in practice these…